promptshield.redact_text

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It only states the action, omitting details on what constitutes sensitive spans, redaction format, side effects (e.g., mutability), permission requirements, or idempotency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and front-loaded. However, it is too minimal to be maximally effective, lacking necessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has one complex parameter, no schema descriptions, no output schema, and no annotations, the description is severely incomplete. It fails to explain how to use the tool, what inputs are expected, or what outputs occur.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'payload' is an object with additionalProperties true and no schema description. The description adds no meaning beyond 'from text', failing to specify expected structure or how to provide text for redaction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it scans and redacts sensitive spans from text, which is a clear verb+resource combination. It distinguishes from siblings: evaluate_policy, scan_messages, and scan_text do not mention redaction. However, 'sensitive spans' is somewhat vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus its siblings. The description provides no context for when redaction is appropriate or when to prefer alternative tools like scan_text for scanning only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.